Adaptable state based control system
First Claim
1. An autonomous system that is controlled based on temporal constraints placed upon the behavior of the autonomous system and statistically indeterminate knowledge about the behavior of the autonomous system, the autonomous system comprising:
- multiple hardware proxies which provide an interface between a controller and system hardware;
a statistical state estimator, which provides statistical estimated values and estimated uncertainty values of the state of the system and the controller in response to temporal and behavior constraints and based upon measurements received from the hardware proxies;
a control executor that is configured to issue commands to the hardware proxies based upon temporal and behavioral constraints on the system, the statistical estimated values, and the estimated uncertainty values;
a state knowledge manager which is configured to coordinate the use the statistical estimates and uncertainties the state of the system; and
a set of common models for the behavior of the system, the controller, and the external environment, wherein the common models are used by the state estimator, the control executor, and the state knowledge manager.
2 Assignments
0 Petitions
Accused Products
Abstract
An autonomous controller, comprised of a state knowledge manager, a control executor, hardware proxies and a statistical estimator collaborates with a goal elaborator, with which it shares common models of the behavior of the system and the controller. The elaborator uses the common models to generate from temporally indeterminate sets of goals, executable goals to be executed by the controller. The controller may be updated to operate in a different system or environment than that for which it was originally designed by the replacement of shared statistical models and by the instantiation of a new set of state variable objects derived from a state variable class. The adaptation of the controller does not require substantial modification of the goal elaborator for its application to the new system or environment.
-
Citations
37 Claims
-
1. An autonomous system that is controlled based on temporal constraints placed upon the behavior of the autonomous system and statistically indeterminate knowledge about the behavior of the autonomous system, the autonomous system comprising:
-
multiple hardware proxies which provide an interface between a controller and system hardware;
a statistical state estimator, which provides statistical estimated values and estimated uncertainty values of the state of the system and the controller in response to temporal and behavior constraints and based upon measurements received from the hardware proxies;
a control executor that is configured to issue commands to the hardware proxies based upon temporal and behavioral constraints on the system, the statistical estimated values, and the estimated uncertainty values;
a state knowledge manager which is configured to coordinate the use the statistical estimates and uncertainties the state of the system; and
a set of common models for the behavior of the system, the controller, and the external environment, wherein the common models are used by the state estimator, the control executor, and the state knowledge manager. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A method of autonomous control which shares information about a set of state variables with a goal elaborator and a controller, the method comprising:
-
generating with a goal elaborator, desired values associated with a set of state variables wherein the state variables define the condition of an autonomous device;
generating with a controller, estimated values associated with the set of state variables;
generating with the controller, estimated uncertainty values associated with the estimate values; and
sharing with the goal elaborator and the controller, the desired values, the estimated values, and the estimated uncertainty values. - View Dependent Claims (10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 28, 29, 30)
-
-
15. A method of control comprising:
-
generating with an elaborator, a set of desired values that are associated with a set of state variables;
generating with a controller, a set of estimated values that are associated with the set of state variables;
generating with a controller, a set of estimated uncertainty values that are associated with the estimate values; and
sharing with both the elaborator and controller, the desired values, the estimated values, and the estimated uncertainty values.
-
-
23. A method of autonomous control that combines temporal elaboration with statistical modeling, the method comprising:
-
generating with a controller statistically estimated values associated with a set of state variables;
generating with a controller statistically estimated uncertainty values associated with the statistically estimated values; and
generating with a goal elaborator a set of desired values associated with a set of state variables wherein the act of generating the desired values is based on the statistically estimate values, statistically estimated uncertainty values and a set of temporally indeterminate goals.
-
-
25. A method of autonomous control that combines temporal elaboration with statistical modeling, the method comprising:
-
generating with an elaborator based on a set of temporally indeterminate goals, desired values associated with a set of state variables; and
generating with a controller statistically estimated values associated with the set of state variables wherein the act of generating the statistically estimated values is based on statistical models associated with the controller and the desired values generated by the elaborator.
-
-
27. A control apparatus comprising:
-
an elaborator which is configured to generate a set of desired values, wherein the set of desired values are associated with a set of state variables;
a controller which is configured to generate a set of estimated values that are associated with the set of state variables, the controller further configured to generate a set of estimated uncertainty values that are associated with the estimate values; and
wherein the controller and elaborator are configured to share the desired values, the estimated values, and the estimated uncertainty values.
-
-
31. A method of reconfiguring a controller and an elaborator associated with a first autonomous system so that the controller and elaborator can direct a second autonomous system, the method comprising:
-
replacing a first set of state variables associated with a first autonomous system with a second set of state variables associated with a second autonomous system;
replacing a first set of statistical models associated with the first set of state variables with a second set of statistical models associated with the second set of state variables; and
automatically sharing with the elaborator and controller, data associated with the second set of state variables.
-
-
32. An method of adapting the use of an autonomous controller configured to operate within a first system for a second system, wherein the adaptation comprises:
-
(A) replacing a first set of state variables associated with a first system and with a second set of state variables associated with a second system;
(B) identifying attribute values associated with members of the second set of state variables;
(C) replacing a first set of statistical models that estimate and predict the behavior of the first system with a second set of statistical models that estimate the behavior of the second system;
(D) replacing a first set of models for the behavior of sensors and actuators in the first system with a second set of models of the behavior of sensors and actuators in the second system; and
(E) sharing with an elaborator and a controller, the second set of state variables and the behavior of the second system predicted by the statistical models. - View Dependent Claims (33, 34, 35, 36, 37)
-
Specification